Derivation of theta-angle and geometric transformation for skew correction using homography matrix

Sharma, Divya; Sharma, Shilpa; Bhavnagar, Vaibhav

doi:10.47974/JIM-2503

Open Access Research Article

Derivation of theta-angle and geometric transformation for skew correction using homography matrix

Divya Sharmadivya.sharma.orp@chitkara.edu.inDepartment of Computer Applications Manipal University JaipurCentre of Research Impact and Outcome Chitkara UniversityRajpura, Punjab, 140417, IndiaView full profile → , ^*Shilpa SharmaCorresponding authorshilpa.sharma@jaipur.manipal.eduDepartment of Computer Applications Manipal University JaipurDepartment of Computer Applications Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , Vaibhav Bhavnagarvaibhav.bhatnagar@jaipur.manipal.eduDepartment of Computer Applications Manipal University JaipurDepartment of Computer Applications Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 681–692Vol. 29Issue 3March 2026DOI: 10.47974/JIM-2503XML

Received:: 01 Apr 2025
Published Online:: 18 Mar 2026
Article type:: Research Article
Language:: EN
Article no.:: JIM-2503
Pages:: 681–692

Abstract

Detecting tilted and skewed vehicle license plates is a significant challenge, often leading to reduced detection accuracy. Traditional detection models struggle with such variations, affecting the efficiency of automated license plate monitoring systems. This research devised a novel skewed license plate detection model that effectively addresses the issue of tilted and skewed license plates. The proposed model calculates the four coordinates and the centroid coordinates of each plate. To differentiate the angular distortion of the tilted plates, the inverse of theta is calculated to convert the slope into an angle. Based on estimated angles the license plates are categorized as straight horizontal (𝜃 ≈ 0°), clockwise skewed (𝜃 > 0°) and anticlockwise skewed (𝜃 < 0°). The tilted coordinates then transform the quadrilateral plate into a rectangular shape using the homography matrix. Applied to a dataset of 1100 vehicle images with varied skewed and complex weather conditioned images, the model demonstrates enhanced feature extraction and localization precision. Experimental results show 99% detection accuracy, with notable gains in precision, recall, and mAP, outperforming existing methods. The proposed model supports SDG 11: Sustainable Cities and Communities through enhanced intelligent traffic systems.

Keywords

Homography matrix Tilted Rotation matrix Affine transformation Perspective transformation

Subject Classifications

94A08

References

[1] H. Li, P. Wang, and C. Shen, “Toward End-to-End Car License Plate Detection and Recognition with Deep Neural Networks,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 3, pp. 1126–1136 (Aug. 2019), doi: 10.1109/TITS.2018.2847291.
[2] N. N. Kamal and E. Tariq, “License Plate Tilt Correction: A Review,” Engineering and Technology Journal, vol. 39, no. 1B, pp. 1–8 (2021).
[3] K. Deb, I. Khan, A. Saha, and K.-H. Jo, “An Efficient Method of Vehicle License Plate Recognition Based on Sliding Concentric Windows and Artificial Neural Network,” Procedia Technology, vol. 4, pp. 812–819 (2012).
[4] P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, “A review of YOLO algorithm developments,” Procedia Computer Science, vol. 199, pp. 1066–1073 (2022).
[5] M. Hussain, “YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature Toward Digital Manufacturing and Industrial Defect Detection,” Machines, vol. 11, no. 7, pp. 677 (2023).
[6] J. Terven, D.-M. Córdova-Esparza, and J.-A. Romero-González, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1680–1716 (2023).
[7] S. Parvin, L. J. Rozario, and M. E. Islam, “Vehicle Number Plate Detection and Recognition Techniques: A Review,” Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 423–438 (Mar. 2021), doi: 10.25046/aj060249.
[8] N. Shidore and M. Patwardhan, “Automatic Vehicle Number Plate Recognition System Using Optical Character Recognition and Artificial Neural Network,” International Journal of Computer Applications, vol. 1, no. 21, pp. 28–32 (2010).
[9] P. I. Reji and V. S. Dharun, “License Plate Localization: A Review,” International Journal of Engineering Trends and Technology (IJETT), vol. 10, no. 13, pp. 604–615 (Apr. 2014).
[10] S. A. Pagore and M. S. Deshpande, “Car License Plate Detection,” International Journal of Computer Applications, vol. 128, no. 13, pp. 8–11 (Oct. 2015), doi: 10.5120/ijca2015906716.
[11] X. Zhang, N. Gu, H. Ye, and C. Lin, “Vehicle License Plate Detection and Recognition Using Deep Neural Networks and Generative Adversarial Networks,” Journal of Electronic Imaging, vol. 27, no. 4, pp. 043056 (Aug. 2018), doi: 10.1117/1.JEI.27.4.043056.
[12] Slimani, A. Zaarane, W. Al Okaishi, I. Atouf, and A. Hamdoun, “An automated license plate detection and recognition system based on wavelet decomposition and CNN,” Array, vol. 8, pp. 100040 (2020).
[13] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 779– 788 (2016).
[14] J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 7263–7271 (2017).
[15] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv preprint arXiv:1804.02767 (2018).
[16] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934 (2020).
[17] D. Thuan, Evolution of YOLO Algorithm and YOLOv5: The State-of-the-Art Object Detection Algorithm, Bachelor’s thesis, Oulu University of Applied Sciences, Oulu, Finland (2021).
[18] C. Gupta, N. S. Gill, P. Gulia, and J. M. Chatterjee, “A Novel Finetuned YOLOv6 Transfer Learning Model for Real-Time Object Detection,” Journal of Real-Time Image Processing, vol. 20, article no. 42 (Apr. 2023), doi: 10.1007/s11554-023-01299-3.
[19] B. Sun, K. Bi, and Q. Wang, “YOLOv7-FIRE: A Tiny-Fire Identification and Detection Method Applied on UAV,” AIMS Mathematics, vol. 9, no. 5, pp. 10775–10801 (Mar. 2024), doi: 10.3934/math.2024526.
[20] H. Harjule, P. Priyanka, V. Tiwari, and A. Kumar, “Mathematical models to predict COVID-19 outbreak: An interim review,” Journal of Interdisciplinary Mathematics, vol. 24, no. 2, pp. 259–284 (2021).
[21] C. Meshram, “Modified ID-based public key cryptosystem using double discrete logarithm problem,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 1, no. 6 (2010).
[22] M. Orouskhani, Y. Orouskhani, M. Mansouri, and M. Teshnehlab, “A novel cat swarm optimization algorithm for unconstrained optimization problems,” International Journal of Information Technology and Computer Science, vol. 5, no. 11, pp. 32–41 (2013).

Views: 63Downloads: 8Citations: 0